PyTorchKR Papers

최신 논문

총 1,515편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2403.08216공식 코드 · Papers with Code

PaddingFlow: Improving Normalizing Flows with Padding-Dimensional Noise

Normalizing flow is a generative modeling approach with efficient sampling. However, Flow-based models suffer two issues: 1) If the target distribution is manifold, due to the unmatch between the dimensions of the latent target distribution and the data distribution, flow-based models might perform badly. 2) Discrete data might make flow-based models collapse into a degenerate mixture of point masses. To sidestep such two issues, we propose PaddingFlow, a novel dequantization method, which improves normalizing flows with padding-dimensional noise. To implement PaddingFlow, only the dimension of normalizing flows needs to be modified. Thus, our method is easy to implement and computationally cheap. Moreover, the padding-dimensional noise is only added to the padding dimension, which means PaddingFlow can dequantize without changing data distributions. Implementing existing dequantization methods needs to change data distributions, which might degrade performance. We validate our method on the main benchmarks of unconditional density estimation, including five tabular datasets and four image datasets for Variational Autoencoder (VAE) models, and the Inverse Kinematics (IK) experiments which are conditional density estimation. The results show that PaddingFlow can perform better in all experiments in this paper, which means PaddingFlow is widely suitable for various tasks. The code is available at: https://github.com/AdamQLMeng/PaddingFlow.

arXiv:2403.07207

Tracking Dynamic Gaussian Density with a Theoretically Optimal Sliding Window Approach

Dynamic density estimation is ubiquitous in many applications, including computer vision and signal processing. One popular method to tackle this problem is the "sliding window" kernel density estimator. There exist various implementations of this method that use heuristically defined weight sequences for the observed data. The weight sequence, however, is a key aspect of the estimator affecting the tracking performance significantly. In this work, we study the exact mean integrated squared error (MISE) of "sliding window" Gaussian Kernel Density Estimators for evolving Gaussian densities. We provide a principled guide for choosing the optimal weight sequence by theoretically characterizing the exact MISE, which can be formulated as constrained quadratic programming. We present empirical evidence with synthetic datasets to show that our weighting scheme indeed improves the tracking performance compared to heuristic approaches.

arXiv:2403.04766

Nonparametric Regression under Cluster Sampling

This paper develops a general asymptotic theory for nonparametric kernel regression in the presence of cluster dependence. We examine nonparametric density estimation, Nadaraya-Watson kernel regression, and local linear estimation. Our theory accommodates growing and heterogeneous cluster sizes. We derive asymptotic conditional bias and variance, establish uniform consistency, and prove asymptotic normality. Our findings reveal that under heterogeneous cluster sizes, the asymptotic variance includes a new term reflecting within-cluster dependence, which is overlooked when cluster sizes are presumed to be bounded. We propose valid approaches for bandwidth selection and inference, introduce estimators of the asymptotic variance, and demonstrate their consistency. In simulations, we verify the effectiveness of the cluster-robust bandwidth selection and show that the derived cluster-robust confidence interval improves the coverage ratio. We illustrate the application of these methods using a policy-targeting dataset in development economics.

arXiv:2403.01671

Permutation invariant functions: statistical tests, density estimation, and computationally efficient embedding

Permutation invariance is among the most common symmetry that can be exploited to simplify complex problems in machine learning (ML). There has been a tremendous surge of research activities in building permutation invariant ML architectures. However, less attention is given to: (1) how to statistically test for permutation invariance of coordinates in a random vector where the dimension is allowed to grow with the sample size; (2) how to leverage permutation invariance in estimation problems and how does it help reduce dimensions. In this paper, we take a step back and examine these questions in several fundamental problems: (i) testing the assumption of permutation invariance of multivariate distributions; (ii) estimating permutation invariant densities; (iii) analyzing the metric entropy of permutation invariant function classes and compare them with their counterparts without imposing permutation invariance; (iv) deriving an embedding of permutation invariant reproducing kernel Hilbert spaces for efficient computation. In particular, our methods for (i) and (iv) are based on a sorting trick and (ii) is based on an averaging trick. These tricks substantially simplify the exploitation of permutation invariance.

arXiv:2403.01499공식 코드 · Papers with Code

Normalizing Flow-based Differentiable Particle Filters

Recently, there has been a surge of interest in incorporating neural networks into particle filters, e.g. differentiable particle filters, to perform joint sequential state estimation and model learning for non-linear non-Gaussian state-space models in complex environments. Existing differentiable particle filters are mostly constructed with vanilla neural networks that do not allow density estimation. As a result, they are either restricted to a bootstrap particle filtering framework or employ predefined distribution families (e.g. Gaussian distributions), limiting their performance in more complex real-world scenarios. In this paper we present a differentiable particle filtering framework that uses (conditional) normalizing flows to build its dynamic model, proposal distribution, and measurement model. This not only enables valid probability densities but also allows the proposed method to adaptively learn these modules in a flexible way, without being restricted to predefined distribution families. We derive the theoretical properties of the proposed filters and evaluate the proposed normalizing flow-based differentiable particle filters' performance through a series of numerical experiments.

arXiv:2403.01666

Improving Adversarial Energy-Based Model via Diffusion Process

Generative models have shown strong generation ability while efficient likelihood estimation is less explored. Energy-based models~(EBMs) define a flexible energy function to parameterize unnormalized densities efficiently but are notorious for being difficult to train. Adversarial EBMs introduce a generator to form a minimax training game to avoid expensive MCMC sampling used in traditional EBMs, but a noticeable gap between adversarial EBMs and other strong generative models still exists. Inspired by diffusion-based models, we embedded EBMs into each denoising step to split a long-generated process into several smaller steps. Besides, we employ a symmetric Jeffrey divergence and introduce a variational posterior distribution for the generator's training to address the main challenges that exist in adversarial EBMs. Our experiments show significant improvement in generation compared to existing adversarial EBMs, while also providing a useful energy function for efficient density estimation.

arXiv:2402.17943공식 코드 · Papers with Code

Sequential transport maps using SoS density estimation and $α$-divergences

Transport-based density estimation methods are receiving growing interest because of their ability to efficiently generate samples from the approximated density. We further invertigate the sequential transport maps framework proposed from arXiv:2106.04170 arXiv:2303.02554, which builds on a sequence of composed Knothe-Rosenblatt (KR) maps. Each of those maps are built by first estimating an intermediate density of moderate complexity, and then by computing the exact KR map from a reference density to the precomputed approximate density. In our work, we explore the use of Sum-of-Squares (SoS) densities and $\alpha$-divergences for approximating the intermediate densities. Combining SoS densities with $\alpha$-divergence interestingly yields convex optimization problems which can be efficiently solved using semidefinite programming. The main advantage of $\alpha$-divergences is to enable working with unnormalized densities, which provides benefits both numerically and theoretically. In particular, we provide a new convergence analyses of the sequential transport maps based on information geometric properties of $\alpha$-divergences. The choice of intermediate densities is also crucial for the efficiency of the method. While tempered (or annealed) densities are the state-of-the-art, we introduce diffusion-based intermediate densities which permits to approximate densities known from samples only. Such intermediate densities are well-established in machine learning for generative modeling. Finally we propose low-dimensional maps (or lazy maps) for dealing with high-dimensional problems and numerically demonstrate our methods on Bayesian inference problems and unsupervised learning tasks.

arXiv:2402.17888

ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection

Post-hoc out-of-distribution (OOD) detection has garnered intensive attention in reliable machine learning. Many efforts have been dedicated to deriving score functions based on logits, distances, or rigorous data distribution assumptions to identify low-scoring OOD samples. Nevertheless, these estimate scores may fail to accurately reflect the true data density or impose impractical constraints. To provide a unified perspective on density-based score design, we propose a novel theoretical framework grounded in Bregman divergence, which extends distribution considerations to encompass an exponential family of distributions. Leveraging the conjugation constraint revealed in our theorem, we introduce a \textsc{ConjNorm} method, reframing density function design as a search for the optimal norm coefficient $p$ against the given dataset. In light of the computational challenges of normalization, we devise an unbiased and analytically tractable estimator of the partition function using the Monte Carlo-based importance sampling technique. Extensive experiments across OOD detection benchmarks empirically demonstrate that our proposed \textsc{ConjNorm} has established a new state-of-the-art in a variety of OOD detection setups, outperforming the current best method by up to 13.25$\%$ and 28.19$\%$ (FPR95) on CIFAR-100 and ImageNet-1K, respectively.

arXiv:2402.11589

CowScape: Quantitative reconstruction of the conformational landscape of biological macromolecules from cryo-EM data

Cryo-EM data processing typically focuses on the structure of the main conformational state under investigation and discards images that belong to other states. This approach can reach atomic resolution, but ignores vast amounts of valuable information about the underlying conformational ensemble and its dynamics. CowScape analyzes an entire cryo-EM dataset and thereby obtains a quantitative description of structural variability of macromolecular complexes that represents the biochemically relevant conformational space. By combining extensive image classification with principal component analysis (PCA) of the classified 3D volumes and kernel density estimation, CowScape can be used as a quantitative tool to analyze this variability. PCA projects all 3D structures along the major modes spanning a low-dimensional space that captures a large portion of structural variability. The number of particle images in a given state can be used to calculate an energy landscape based on kernel density estimation and Boltzmann inversion. By revealing allosteric interactions in macromolecular complexes, CowScape allows us to distinguish and interpret dynamic changes in macromolecular complexes during function and regulation.

arXiv:2402.11552

Empirical Density Estimation based on Spline Quasi-Interpolation with applications to Copulas clustering modeling

Density estimation is a fundamental technique employed in various fields to model and to understand the underlying distribution of data. The primary objective of density estimation is to estimate the probability density function of a random variable. This process is particularly valuable when dealing with univariate or multivariate data and is essential for tasks such as clustering, anomaly detection, and generative modeling. In this paper we propose the mono-variate approximation of the density using spline quasi interpolation and we applied it in the context of clustering modeling. The clustering technique used is based on the construction of suitable multivariate distributions which rely on the estimation of the monovariate empirical densities (marginals). Such an approximation is achieved by using the proposed spline quasi-interpolation, while the joint distributions to model the sought clustering partition is constructed with the use of copulas functions. In particular, since copulas can capture the dependence between the features of the data independently from the marginal distributions, a finite mixture copula model is proposed. The presented algorithm is validated on artificial and real datasets.

arXiv:2402.11778

Towards Theoretical Understandings of Self-Consuming Generative Models

This paper tackles the emerging challenge of training generative models within a self-consuming loop, wherein successive generations of models are recursively trained on mixtures of real and synthetic data from previous generations. We construct a theoretical framework to rigorously evaluate how this training procedure impacts the data distributions learned by future models, including parametric and non-parametric models. Specifically, we derive bounds on the total variation (TV) distance between the synthetic data distributions produced by future models and the original real data distribution under various mixed training scenarios for diffusion models with a one-hidden-layer neural network score function. Our analysis demonstrates that this distance can be effectively controlled under the condition that mixed training dataset sizes or proportions of real data are large enough. Interestingly, we further unveil a phase transition induced by expanding synthetic data amounts, proving theoretically that while the TV distance exhibits an initial ascent, it declines beyond a threshold point. Finally, we present results for kernel density estimation, delivering nuanced insights such as the impact of mixed data training on error propagation.

arXiv:2402.07048공식 코드 · Papers with Code

Logistic-beta processes for dependent random probabilities with beta marginals

The beta distribution serves as a canonical tool for modeling probabilities in statistics and machine learning. However, there is limited work on flexible and computationally convenient stochastic process extensions for modeling dependent random probabilities. We propose a novel stochastic process called the logistic-beta process, whose logistic transformation yields a stochastic process with common beta marginals. Logistic-beta processes can model dependence on both discrete and continuous domains, such as space or time, and have a flexible dependence structure through correlation kernels. Moreover, its normal variance-mean mixture representation leads to effective posterior inference algorithms. We show how the proposed logistic-beta process can be used to design computationally tractable dependent Bayesian nonparametric models, including dependent Dirichlet processes and extensions. We illustrate the benefits through nonparametric binary regression and conditional density estimation examples, both in simulation studies and in a pregnancy outcome application.

arXiv:2402.06537

Feature Density Estimation for Out-of-Distribution Detection via Normalizing Flows

Out-of-distribution (OOD) detection is a critical task for safe deployment of learning systems in the open world setting. In this work, we investigate the use of feature density estimation via normalizing flows for OOD detection and present a fully unsupervised approach which requires no exposure to OOD data, avoiding researcher bias in OOD sample selection. This is a post-hoc method which can be applied to any pretrained model, and involves training a lightweight auxiliary normalizing flow model to perform the out-of-distribution detection via density thresholding. Experiments on OOD detection in image classification show strong results for far-OOD data detection with only a single epoch of flow training, including 98.2% AUROC for ImageNet-1k vs. Textures, which exceeds the state of the art by 7.8%. We additionally explore the connection between the feature space distribution of the pretrained model and the performance of our method. Finally, we provide insights into training pitfalls that have plagued normalizing flows for use in OOD detection.

arXiv:2402.04278공식 코드 · Papers with Code

Gaussian Plane-Wave Neural Operator for Electron Density Estimation

This work studies machine learning for electron density prediction, which is fundamental for understanding chemical systems and density functional theory (DFT) simulations. To this end, we introduce the Gaussian plane-wave neural operator (GPWNO), which operates in the infinite-dimensional functional space using the plane-wave and Gaussian-type orbital bases, widely recognized in the context of DFT. In particular, both high- and low-frequency components of the density can be effectively represented due to the complementary nature of the two bases. Extensive experiments on QM9, MD, and material project datasets demonstrate GPWNO's superior performance over ten baselines.

arXiv:2402.03845

On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion models

Diffusion models are generative models that have recently demonstrated impressive performances in terms of sampling quality and density estimation in high dimensions. They rely on a forward continuous diffusion process and a backward continuous denoising process, which can be described by a time-dependent vector field and is used as a generative model. In the original formulation of the diffusion model, this vector field is assumed to be the score function (i.e. it is the gradient of the log-probability at a given time in the diffusion process). Curiously, on the practical side, most studies on diffusion models implement this vector field as a neural network function and do not constrain it be the gradient of some energy function (that is, most studies do not constrain the vector field to be conservative). Even though some studies investigated empirically whether such a constraint will lead to a performance gain, they lead to contradicting results and failed to provide analytical results. Here, we provide three analytical results regarding the extent of the modeling freedom of this vector field. {Firstly, we propose a novel decomposition of vector fields into a conservative component and an orthogonal component which satisfies a given (gauge) freedom. Secondly, from this orthogonal decomposition, we show that exact density estimation and exact sampling is achieved when the conservative component is exactly equals to the true score and therefore conservativity is neither necessary nor sufficient to obtain exact density estimation and exact sampling. Finally, we show that when it comes to inferring local information of the data manifold, constraining the vector field to be conservative is desirable.

arXiv:2402.02482

Decomposing Global Bank Network Connectedness: What is Common, Idiosyncratic and When?

We propose a novel approach to estimate high-dimensional global bank network connectedness in both the time and frequency domains. By employing a factor model with sparse VAR idiosyncratic components, we decompose system-wide connectedness (SWC) into two key drivers: (i) common component shocks and (ii) idiosyncratic shocks. We also provide bootstrap confidence bands for all SWC measures. Furthermore, spectral density estimation allows us to disentangle SWC into short-, medium-, and long-term frequency responses to these shocks. We apply our methodology to two datasets of daily stock price volatilities for over 90 global banks, spanning the periods 2003-2013 and 2014-2023. Our empirical analysis reveals that SWC spikes during global crises, primarily driven by common component shocks and their short term effects. Conversely, in normal times, SWC is largely influenced by idiosyncratic shocks and medium-term dynamics.

arXiv:2402.03142공식 코드 · Papers with Code

Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language Models

Neural network pruning has become increasingly crucial due to the complexity of these models and their widespread use in various fields. Existing pruning algorithms often suffer from limitations such as architecture specificity, excessive complexity and reliance on demanding calculations, rendering them impractical for real-world applications. This paper introduces KEN: a straightforward, universal and unstructured pruning algorithm based on Kernel Density Estimation (KDE). KEN aims to construct optimized transformers by selectively preserving the most significant parameters while restoring others to their pre-training state. This strategy preserves model performance while enabling storage of only the optimized subnetwork, leading to substantial memory savings. Extensive evaluations across seven different LLMs demonstrate that KEN achieves equal or better performance than their original unpruned versions, with a minimum parameter reduction of 25%. Furthermore, in-depth comparisons with established pruning and PEFT algorithms confirm KEN effectiveness. We further introduce KEN$_{viz}$, an explainable tool that visualizes the optimized model composition achieved by KEN from different points of view.

arXiv:2402.03138공식 코드 · Papers with Code

Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations

In this paper we adopt a representation-centric perspective on exploration in reinforcement learning, viewing exploration fundamentally as a density estimation problem. We investigate the effectiveness of clustering representations for exploration in 3-D environments, based on the observation that the importance of pixel changes between transitions is less pronounced in 3-D environments compared to 2-D environments, where pixel changes between transitions are typically distinct and significant. We propose a method that performs episodic and global clustering on random representations and on pre-trained DINO representations to count states, i.e, estimate pseudo-counts. Surprisingly, even random features can be clustered effectively to count states in 3-D environments, however when these become visually more complex, pre-trained DINO representations are more effective thanks to the pre-trained inductive biases in the representations. Overall, this presents a pathway for integrating pre-trained biases into exploration. We evaluate our approach on the VizDoom and Habitat environments, demonstrating that our method surpasses other well-known exploration methods in these settings.

arXiv:2402.01460공식 코드 · Papers with Code

Deep conditional distribution learning via conditional Föllmer flow

We introduce an ordinary differential equation (ODE) based deep generative method for learning conditional distributions, named Conditional F\"ollmer Flow. Starting from a standard Gaussian distribution, the proposed flow could approximate the target conditional distribution very well when the time is close to 1. For effective implementation, we discretize the flow with Euler's method where we estimate the velocity field nonparametrically using a deep neural network. Furthermore, we also establish the convergence result for the Wasserstein-2 distance between the distribution of the learned samples and the target conditional distribution, providing the first comprehensive end-to-end error analysis for conditional distribution learning via ODE flow. Our numerical experiments showcase its effectiveness across a range of scenarios, from standard nonparametric conditional density estimation problems to more intricate challenges involving image data, illustrating its superiority over various existing conditional density estimation methods.

arXiv:2402.01450

Improving importance estimation in covariate shift for providing accurate prediction error

In traditional Machine Learning, the algorithms predictions are based on the assumption that the data follows the same distribution in both the training and the test datasets. However, in real world data this condition does not hold and, for instance, the distribution of the covariates changes whereas the conditional distribution of the targets remains unchanged. This situation is called covariate shift problem where standard error estimation may be no longer accurate. In this context, the importance is a measure commonly used to alleviate the influence of covariate shift on error estimations. The main drawback is that it is not easy to compute. The Kullback-Leibler Importance Estimation Procedure (KLIEP) is capable of estimating importance in a promising way. Despite its good performance, it fails to ignore target information, since it only includes the covariates information for computing the importance. In this direction, this paper explores the potential performance improvement if target information is considered in the computation of the importance. Then, a redefinition of the importance arises in order to be generalized in this way. Besides the potential improvement in performance, including target information make possible the application to a real application about plankton classification that motivates this research and characterized by its great dimensionality, since considering targets rather than covariates reduces the computation and the noise in the covariates. The impact of taking target information is also explored when Logistic Regression (LR), Kernel Mean Matching (KMM), Ensemble Kernel Mean Matching (EKMM) and the naive predecessor of KLIEP called Kernel Density Estimation (KDE) methods estimate the importance. The experimental results lead to a more accurate error estimation using target information, especially in case of the more promising method KLIEP.